Model comparison
Llama 2-7B vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 29.1 on the Noometry Index.
Last verified . 15 shared benchmarks.
MetaSummary
- They share 15 benchmarks with published results for both. Llama 2-7B scores higher in 0 categories and MiMo-V2.5-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.3 to 28.0.
Side by side
| Llama 2-7B | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 29.1 | 45.2 |
| Released | 2023-07-18 | 2026-04-22 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.43 |
| Output $ / M tokens | — | $0.87 |
| Results tracked | 29 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Llama 2-7B: 29.2 (#307), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Llama 2-7B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1002 | 1503 |
| LMArena WebDev | — | 1479 |
| SciCode | — | 50.2% |
| ALE-Bench | — | 899.8 |
Reasoning MiMo-V2.5-Pro leads
Llama 2-7B: 15.7 (#312), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Llama 2-7B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1488 |
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| Chess Puzzles | 0% | — |
| DTBench | — | 84.5% |
| LMCA | — | 29.5% |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 99.06 | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math MiMo-V2.5-Pro leads
Llama 2-7B: 30.7 (#233), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Llama 2-7B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1042 | 1481 |
| ProofBench | — | 22% |
| GSM8K | 16.7% | — |
Knowledge MiMo-V2.5-Pro leads
Llama 2-7B: 28.2 (#248), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Llama 2-7B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1036 | 1503 |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, MiMo-V2.5-Pro: —
| Benchmark | Llama 2-7B | MiMo-V2.5-Pro |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual MiMo-V2.5-Pro leads
Llama 2-7B: 23.8 (#293), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Llama 2-7B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 973 | 1449 |
| LMArena Chinese | 973 | 1507 |
| LMArena French | 970 | 1488 |
| LMArena German | 978 | 1458 |
| LMArena Russian | 995 | 1450 |
| LMArena Spanish | 1007 | 1471 |
| LMArena Japanese | — | 1412 |
| LMArena Korean | — | 1437 |
Instruction Following MiMo-V2.5-Pro leads
Llama 2-7B: 50.8 (#298), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Llama 2-7B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1006 | 1477 |
Long Context MiMo-V2.5-Pro leads
Llama 2-7B: 30.4 (#287), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Llama 2-7B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 999 | 1483 |
Writing & Preference MiMo-V2.5-Pro leads
Llama 2-7B: 28.0 (#298), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Llama 2-7B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1053 | 1465 |
| LMArena Creative Writing | 1033 | 1440 |
| LMArena Multi-Turn | 1029 | 1477 |
| EQ-Bench Creative Writing | — | 1493 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Llama 2-7B better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 29.1 on the Noometry Index.
Is Llama 2-7B or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 29.2 in the Noometry coding category.
How many benchmarks do Llama 2-7B and MiMo-V2.5-Pro share?
15 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and MiMo-V2.5-Pro has 27.